Back to Nodes
Flux Schnell

Flux Schnell

Official

The fastest image generation model, perfect for quick prototyping and personal projects.

Nodespell AI
AI / Image / Black Forest Labs

The fastest image generation model, perfect for quick prototyping and personal projects.

Model Overview

A highly optimized text-to-image generation model designed for speed and efficiency, suitable for local development and personal use.

Best At

Rapid image generation with competitive prompt following, ideal for quick iterations and experimentation.

Limitations / Not Good At

  • May not provide factual information.
  • Can sometimes amplify societal biases present in training data.
  • Prompt following can be influenced by prompting style.
  • May occasionally fail to generate output that perfectly matches prompts.

Ideal Use Cases

  • Prototyping and concept visualization
  • Personal creative projects
  • Generating draft illustrations
  • Quick mockups

Input & Output Format

Text prompt → Image URLs

Performance Notes

Extremely fast inference, especially when go_fast is enabled (uses fp8 quantization). Outputs are not deterministic when go_fast is true, even with a seed.

Inputs (1)

Prompt

String

Prompt for generated image

Multi InputMin: 0Max: 100
Parameters (10)

Seed

Number

Random seed. Set for reproducible generation. Set to -1 if you want it to be randomly generated.

Default: -1

Prompt

String

Prompt for generated image

Default:

Go Fast

Boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed.

Default: true

Megapixels

String

Approximate number of megapixels for generated image

Default: 1

Num Outputs

Number

Number of outputs to generate

Default: 1

Aspect Ratio

String

Aspect ratio for the generated image

Default: 1:1

Output Format

String

Format of the output images

Default: webp

Output Quality

Number

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

Num Inference Steps

Number

Number of denoising steps. 4 is recommended, and lower number of steps produce lower quality outputs, faster.

Default: 4

Disable Safety Checker

Boolean

Disable safety checker for generated images.

Default: false
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

📍 London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Image / Black Forest Labs

Input

Text

Output

Image

Keywords

Image GenerationAspect ControlResolution ControlMulti Output
Use in Workflow